Zobrazeno 1 - 10
of 12 589
pro vyhledávání: '"Sodhi AS"'
Autor:
Sayana, Krishna, Vasudeva, Raghavendra, Vasilevski, Yuri, Su, Kun, Hebert, Liam, Pham, Hubert, Jash, Ambarish, Sodhi, Sukhdeep
The recent advances in Large Language Model's generation and reasoning capabilities present an opportunity to develop truly conversational recommendation systems. However, effectively integrating recommender system knowledge into LLMs for natural lan
Externí odkaz:
http://arxiv.org/abs/2410.16780
Autor:
Choudhury, Sanjiban, Sodhi, Paloma
While large language models (LLMs) show impressive decision-making abilities, current methods lack a mechanism for automatic self-improvement from errors during task execution. We propose LEAP, an iterative fine-tuning framework that continually impr
Externí odkaz:
http://arxiv.org/abs/2410.05434
Autor:
Hebert, Liam, Kyriakidi, Marialena, Pham, Hubert, Sayana, Krishna, Pine, James, Sodhi, Sukhdeep, Jash, Ambarish
Hybrid recommender systems, combining item IDs and textual descriptions, offer potential for improved accuracy. However, previous work has largely focused on smaller datasets and model architectures. This paper introduces Flare (Fusing Language model
Externí odkaz:
http://arxiv.org/abs/2409.11699
Autor:
Hebert, Liam, Sayana, Krishna, Jash, Ambarish, Karatzoglou, Alexandros, Sodhi, Sukhdeep, Doddapaneni, Sumanth, Cai, Yanli, Kuzmin, Dima
Understanding the nuances of a user's extensive interaction history is key to building accurate and personalized natural language systems that can adapt to evolving user preferences. To address this, we introduce PERSOMA, Personalized Soft Prompt Ada
Externí odkaz:
http://arxiv.org/abs/2408.00960
This paper tackles the multi-vehicle Coverage Path Planning (CPP) problem, crucial for applications like search and rescue or environmental monitoring. Due to its NP-hard nature, finding optimal solutions becomes infeasible with larger problem sizes.
Externí odkaz:
http://arxiv.org/abs/2407.08767
Autor:
Harne, Sarthak, Choudhury, Monjoy Narayan, Rao, Madhav, Srikanth, TK, Mehrotra, Seema, Vashisht, Apoorva, Basu, Aarushi, Sodhi, Manjit
The limited availability of psychologists necessitates efficient identification of individuals requiring urgent mental healthcare. This study explores the use of Natural Language Processing (NLP) pipelines to analyze text data from online mental heal
Externí odkaz:
http://arxiv.org/abs/2406.00314
Autor:
Tholoniat, Pierre, Kostopoulou, Kelly, McNeely, Peter, Sodhi, Prabhpreet Singh, Varanasi, Anirudh, Case, Benjamin, Cidon, Asaf, Geambasu, Roxana, Lécuyer, Mathias
Publikováno v:
In ACM SIGOPS 30th Symposium on Operating Systems Principles (SOSP '24), November 4-6, 2024, Austin, TX, USA. ACM, New York, NY, USA, 27 pages
With the impending removal of third-party cookies from major browsers and the introduction of new privacy-preserving advertising APIs, the research community has a timely opportunity to assist industry in qualitatively improving the Web's privacy. Th
Externí odkaz:
http://arxiv.org/abs/2405.16719
Autor:
Rathinasamy, Kamalkumar, Nettar, Jayarama, Kumar, Amit, Manchanda, Vishal, Vijayakumar, Arun, Kataria, Ayush, Manjunath, Venkateshprasanna, GS, Chidambaram, Sodhi, Jaskirat Singh, Shaikh, Shoeb, Khan, Wasim Akhtar, Singh, Prashant, Ige, Tanishq Dattatray, Tiwari, Vipin, Mondal, Rajab Ali, K, Harshini, Reka, S, Amancharla, Chetana, Rahman, Faiz ur, A, Harikrishnan P, Saha, Indraneel, Tiwary, Bhavya, Patel, Navin Shankar, S, Pradeep T, J, Balaji A, Priyapravas, Tarafdar, Mohammed Rafee
Enterprises grapple with the significant challenge of managing proprietary unstructured data, hindering efficient information retrieval. This has led to the emergence of AI-driven information retrieval solutions, designed to adeptly extract relevant
Externí odkaz:
http://arxiv.org/abs/2406.00010
Video creation has become increasingly popular, yet the expertise and effort required for editing often pose barriers to beginners. In this paper, we explore the integration of large language models (LLMs) into the video editing workflow to reduce th
Externí odkaz:
http://arxiv.org/abs/2402.10294
Modeling long histories plays a pivotal role in enhancing recommendation systems, allowing to capture user's evolving preferences, resulting in more precise and personalized recommendations. In this study we tackle the challenges of modeling long use
Externí odkaz:
http://arxiv.org/abs/2401.04858